Basic flow calculation method and device for conductivity-deficient region

Abstract

The invention discloses a base flow calculation method and device for a conductivity-deficient region, relates to the technical field of hydrological research, and aims to solve the problem that a conductivity mass balance method cannot be applied to the conductivity-deficient region for base flow calculation in the prior art. The method comprises the steps of obtaining target hydrological feature data of a target station, wherein the target station is a region which is similar to a preset station in environmental feature and is deficient in conductivity; performing contribution degree identification on the target hydrological feature data by using a feature contribution degree identification model to obtain target parameter combination data for conductivity regression of the target site; on the basis of the target time scale, conductivity regression prediction is carried out by using the conductivity regression model in combination with the target parameter combination data, and target conductivity regression data is obtained; and finally, carrying out base flow segmentation calculation on the target site by adopting a conductivity mass balance method to obtain the base flow of the target site. Therefore, a conductivity mass balance method can be adopted to carry out base flow calculation on an area with deficient conductivity.

Description

Technical Field

[0001] The invention relates to the technical field of hydrological research, and relates to a base flow calculation method and a device for areas lacking electrical conductivity. Background Art

[0002] For a rainfall process in a basin, the flow process line formed at the outlet section of the basin is composed of different water sources. How to distinguish the different components of runoff and their proportions requires dividing the runoff into surface runoff and baseflow, that is, baseflow segmentation. Baseflow segmentation is a basic problem in engineering hydrology and applied hydrology. Its segmentation results are not only an important research content for runoff calculation and hydrological simulation, but also have a significant impact on industrial and agricultural water supply, water security, water resources evaluation, pollutant migration, and river ecological environment protection. Baseflow is composed of regional deep groundwater, shallow groundwater on the river bank, mid-soil flow, soil water, and riverbank return flow. It is the minimum amount of water that a river can maintain during the dry season. As an important part of river flow, baseflow is crucial to our understanding of hydrological processes and the protection and management of surface water resources. Accurate baseflow segmentation is of great significance. However, baseflow cannot be measured directly and can only be estimated indirectly from river flow through some methods.

[0003] At present, the main baseflow segmentation methods include non-tracer and tracer methods. Among them, the non-tracer method represented by the ECK (Asseparation method developed by Eckhardt, ECK) method separates the high-frequency signals from the low-frequency signals in the water flow, and then divides the runoff into direct runoff and underground runoff. However, due to the subjective determination of its parameter values, it is impossible to accurately estimate the baseflow; while the tracer method assumes that the water flow is composed of different water flow components, each of which has a characteristic concentration of one or more conservative chemical components, and the baseflow can be obtained by segmenting according to the characteristic concentrations of different water flow components. Compared with other chemical components, electrical conductivity (EC) is relatively easy to measure and has a correlation with rivers; therefore, the conductivity mass balance (CMB) method using EC as a tracer is currently the most accurate baseflow segmentation method and is widely used in areas with rich conductivity for high-precision calculation of baseflow; however, this method requires that the site has contemporaneous, daily-scale flow and EC data; however, the EC data of sites in most parts of the world are measured once a month or even once a quarter, and EC monitoring generally exhibits strong intermittency and low resolution, making it impossible to use the CMB method for baseflow calculation, which limits the widespread application of the CMB method.

[0004] In order to solve the problem that the CMB method is difficult to use in areas with scarce EC data, most existing solutions construct a functional relationship between flow and EC, regress the EC time series data, and then combine the regressed EC with the CMB method formula to calculate the base flow. Although this method is simple and easy to use, due to the regional specificity of flow changes, the constructed regression relationship is difficult to promote in other areas, and these relationships cannot simultaneously reflect the complex effects of multiple parameters such as climate and watershed characteristics on EC. Therefore, it is not suitable for accurate regression of EC at large quantities of long-sequence stations. There is still a problem that the CMB method cannot be applied to areas with scarce conductivity for base flow calculation.

[0005] Therefore, it is necessary to design a calculation scheme for baseflow in areas with scarce conductivity data, taking into account regional environmental parameters and filling the gaps in EC time series data measurements, so that the CMB method can be used to calculate baseflow; and to solve the problem in the existing technology that the CMB method cannot be applied to areas with scarce conductivity for baseflow calculation. Summary of the invention

[0006] The purpose of the present invention is to provide a method and device for calculating base flow in areas with insufficient conductivity, which fills the gaps between EC time series data measurement values ​​in areas with insufficient conductivity according to environmental parameters, such as basin properties and climatic conditions; thus, it is suitable for regression EC of a large number of long-sequence sites, fills the gaps in EC time series data measurement values, and thus the CMB method can be used for base flow calculation, solving the problem in the prior art that the CMB method cannot be applied to areas with insufficient conductivity for base flow calculation.

[0007] In order to achieve the above object, the present invention provides the following technical solutions:

[0008] In a first aspect, the present invention provides a method for calculating baseflow in a conductivity-deficient area, which may include:

[0009] Obtaining target hydrological characteristic data of a target site, wherein the target hydrological characteristic data at least includes dynamic environmental parameters and static environmental parameters related to base flow generation; the target site is an area with similar environmental characteristics to the preset site and lacking in electrical conductivity;

[0010] The target hydrological characteristic data is identified for contribution by using a characteristic contribution identification model to obtain target parameter combination data for conductivity regression of the target site; the target parameter combination data represents parameter combination data whose conductivity regression contribution is greater than a preset threshold;

[0011] Based on the target parameter combination data, according to the target time scale, a conductivity regression model is used to perform prediction to obtain target conductivity regression data for the target site;

[0012] Based on the target hydrological characteristic data and target conductivity regression data, the conductivity mass balance method is used to perform base flow segmentation calculation on the target site to obtain the base flow of the target site.

[0013] In a second aspect, the present invention provides a base flow calculation device for use in areas lacking electrical conductivity, which may include:

[0014] An acquisition module, the acquisition module is used to acquire target hydrological characteristic data of a target site, the target hydrological characteristic data at least including dynamic environmental parameters and static environmental parameters related to base flow generation; the target site is an area with similar environmental characteristics to the preset site and lacking conductivity;

[0015] A contribution recognition module, wherein the contribution recognition module is used to identify the contribution of the target hydrological characteristic data using a characteristic contribution recognition model to obtain target parameter combination data for conductivity regression of the target site; the target parameter combination data represents parameter combination data whose conductivity regression contribution is greater than a preset threshold;

[0016] A conductivity regression prediction module, which is used to predict the target conductivity regression data for the target site by using a conductivity regression model based on the target parameter combination data and according to the target time scale;

[0017] A calculation module is used to perform base flow segmentation calculation on the target site by using a conductivity mass balance method based on the target hydrological characteristic data and the target conductivity regression data to obtain the base flow of the target site.

[0018] Compared with the prior art, the present invention provides a method for calculating baseflow in areas with a lack of electrical conductivity. The method obtains target hydrological characteristic data of a target site, wherein the target hydrological characteristic data at least includes dynamic environmental parameters and static environmental parameters related to baseflow generation; the target site is an area with similar environmental characteristics to a preset site and lacks electrical conductivity; firstly, a characteristic contribution recognition model is used to identify the contribution of the target hydrological characteristic data to obtain target parameter combination data for electrical conductivity regression of the target site; the target parameter combination data represents parameter combination data whose conductivity regression contribution is greater than a preset threshold; further, based on the target time scale, the conductivity regression model is used to identify the target parameter combination data. Conductivity regression prediction is performed to obtain target conductivity regression data for the target site; finally, based on the target hydrological characteristic data and the target conductivity regression data, the CMB method is used to perform baseflow segmentation calculation on the target site to obtain the baseflow of the target site; based on this, the pre-established feature contribution recognition model and the conductivity regression model can be used to obtain the target conductivity regression data in the conductivity-deficient area, fill the missing EC time series data measurement values, and obtain the regression EC of a large number of long-sequence sites at the target time scale, so that the CMB method can be used to calculate the baseflow, which realizes the use of the CMB method to calculate the baseflow in the conductivity-deficient area and expands the application scope of the CMB method. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0020] Figure 1 A main flow chart of a method for calculating base flow in areas lacking electrical conductivity provided by the present invention;

[0021] Figure 2 A comparison diagram of model regression EC and measured EC for a base flow calculation method for conductivity-deficient areas provided by the present invention;

[0022] Figure 3 A comparison chart of base flow calculation method for conductivity-deficient areas provided by the present invention and base flow calculated by ECK empirical value method;

[0023] Figure 4 A schematic structural diagram of a base flow calculation device for use in areas with a lack of electrical conductivity provided by the present invention. DETAILED DESCRIPTION

[0024] In order to facilitate the clear description of the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, the words "first", "second" and the like are used to distinguish the same items or similar items with substantially the same functions and effects. For example, the first threshold and the second threshold are only used to distinguish different thresholds, and do not limit their order of precedence. Those skilled in the art can understand that the words "first", "second" and the like do not limit the quantity and execution order, and the words "first", "second" and the like do not necessarily limit them to be different.

[0025] It should be noted that, in the present invention, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0026] In the present invention, "at least one" means one or more, and "plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the associated objects in the previous time are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can mean: a, b, c, the combination of a and b, the combination of a and c, the combination of b and c, or the combination of a, b and c, where a, b, c can be single or multiple.

[0027] In the prior art, the high-precision CMB method needs to assume that (a) the characteristic concentrations of different stream components are completely different; (b) the tracer does not react during the medium transmission through the catchment area; (c) the different components are always completely mixed in the river; this method requires the station to have contemporaneous, daily-scale flow and EC data. However, the EC data of stations in most parts of the world are measured once a month or even once a quarter, and EC monitoring is generally intermittent (monitoring is only carried out during flood or drought seasons or specific events) and has a low resolution, which limits the widespread application of the CMB method and makes it impossible to apply the CMB method to baseflow segmentation calculations in areas where EC data is lacking. In order to address the problem that the CMB method is difficult to use in areas where EC data is lacking, most existing solutions construct a functional relationship between flow and EC, regress to obtain EC time series data, and then combine the regressed EC with the CMB method formula to calculate the baseflow. Although this method is simple and easy to use, the constructed regression equations are difficult to generalize to other regions due to the regional specificity of flow changes. Moreover, these equations cannot simultaneously reflect the complex effects of multiple parameters such as climate and watershed characteristics on EC. Therefore, they are not suitable for accurate regression of EC of large quantities of long-sequence stations, which limits the accuracy of the CMB method. Machine learning can integrate multi-index data and extract regularities from them, and has been widely used in many hydrological fields. However, until now, no research has attempted to fill the gaps between EC time series data measurements based on watershed attributes and climate conditions by applying machine learning algorithms.

[0028] Based on this, the present invention proposes a method and device for calculating baseflow in areas with insufficient EC data in combination with a machine learning algorithm; by constructing a feature contribution recognition model and an EC regression model in advance based on areas with sufficient EC data and similar environments, EC regression data that meets the requirements of the CMB method is obtained, so that the high-precision CMB method can be used to perform baseflow segmentation calculations on areas with insufficient conductivity without affecting the calculation accuracy of the CMB method; the problem that the CMB method in the prior art cannot be applied to areas with insufficient conductivity for baseflow calculations is solved.

[0029] Next, the technical solution of the present invention is described in detail with reference to the accompanying drawings:

[0030] See also Figure 1 , Figure 1 This is a main flow chart of a method for calculating base flow in areas with insufficient conductivity provided by the present invention. It should be noted that the method for calculating base flow in areas with insufficient conductivity provided by the present invention is applied to areas with environmental characteristics similar to those of preset sites and insufficient conductivity; its execution subject is a server or terminal device equipped with the technical solution disclosed in the embodiment of the present invention, such as a computing service platform or a handheld computing device, etc.

[0031] exist Figure 1 In, the method may include:

[0032] Step 110: Obtain target hydrological characteristic data of a target site, wherein the target hydrological characteristic data at least includes dynamic environmental parameters and static environmental parameters related to base flow generation; the target site is an area with environmental characteristics similar to those of a preset site and lacking in electrical conductivity.

[0033] In step 110, the preset site is an area with sufficient conductivity and meets the requirements of base flow segmentation calculation using the high-precision CMB method, such as the Missouri River in the United States; the target site is an area with environmental characteristics similar to those of the preset site and lacking conductivity; thus, the EC regression model constructed using the environmental characteristics of the preset site can be introduced to introduce the environmental characteristic information of the target site to perform conductivity prediction, thereby making up for the missing EC time series data measurement values ​​in the conductivity-deficient area and obtaining the EC time series data required for base flow calculation using the CMB method.

[0034] Step 120: Use a feature contribution recognition model to identify the contribution of the target hydrological feature data to obtain target parameter combination data for conductivity regression of the target site; the target parameter combination data represents parameter combination data whose conductivity regression contribution is greater than a preset threshold.

[0035] Step 130: Based on the target parameter combination data and according to the target time scale, a conductivity regression model is used to perform prediction to obtain target conductivity regression data for the target site.

[0036] Step 140: Based on the target hydrological characteristic data and the target conductivity regression data, the CMB method is used to perform base flow segmentation calculation on the target site to obtain the base flow of the target site.

[0037] In step 120 to step 140, the characteristic contribution recognition model and the conductivity regression model are network models constructed based on the hydrological characteristic data of the preset site and are pre-set in the server. When performing base flow segmentation calculation for an area with environmental characteristics similar to the preset site and lacking conductivity, the above two models can be called for identification and prediction, thereby obtaining the conductivity regression data required for the base flow segmentation calculation using the CMB method; thereby, based on the conductivity regression data and the target hydrological characteristic data, the CMB method can be used to perform base flow segmentation calculation on the target site to obtain the base flow of the target site; and the lack of EC in the area will not prevent the high-precision CMB method from being used for base flow segmentation calculation.

[0038] Based on this, the present invention provides a method for calculating baseflow in areas with insufficient conductivity. By utilizing a characteristic contribution recognition model and a conductivity regression model, target conductivity regression data for areas with insufficient conductivity is obtained, the missing values ​​of EC time series data measurement values ​​are filled, and regression EC of a large number of long-sequence sites at a target time scale, such as regression EC at a daily scale, is obtained, so that the CMB method can be used to calculate baseflow. This method realizes that the CMB method can be used to calculate baseflow in areas with insufficient conductivity, thereby broadening the application scope of the CMB method.

[0039] Preferably, in step 110, the dynamic environmental parameters may include at least daily precipitation time series data, temperature time series data, evapotranspiration time series data, flow time series data, and conductivity. The static environmental parameters may include at least altitude, slope, sand ratio, clay ratio, annual average precipitation, annual average temperature, and annual average potential evaporation.

[0040] It should be noted that, in the specific implementation process, a variety of data related to these processes can be collected, not limited to the above data; because the conductivity EC in the dynamic environmental parameters is not daily-scale data, it is impossible to directly use the CMB method for base flow calculation.

[0041] For example, dynamic environmental parameters including daily precipitation time series and temperature time series can be downloaded from relevant websites such as ERA5-Land, and static environmental parameters including altitude, slope, sand grain ratio, etc. can also be downloaded. For example, if the minimum amount of training set data is determined to be 156 in the relevant research on the Missouri River Basin of the preset site. In this regard, for this target site, at least 156 data related to the generation of EC at weekly intervals can also be collected to carry out subsequent research.

[0042] Preferably, the step of using a characteristic contribution recognition model to identify the contribution of the target hydrological characteristic data to obtain target parameter combination data for conductivity regression of the target site may include:

[0043] The hydrological characteristic data of a preset site is obtained; the preset site is a site whose conductivity satisfies the base flow segmentation calculation using the CMB method; the hydrological characteristic data is divided into ecological zones to obtain multiple ecological zones; the ecological zones are areas with similar environmental characteristics; the environmental characteristics include climate, vegetation, soil type and geological conditions; based on the hydrological characteristic data of the multiple ecological zones, the characteristic contribution recognition model and the conductivity regression model are established.

[0044] As an example, the EC data of the Missouri River Basin in the United States meets the requirements for the basin to be segmented and calculated using the CMB method, and has daily-scale EC data; therefore, the present invention uses the Missouri River Basin in the United States as the research area, constructs a characteristic contribution recognition model and a conductivity regression model, and stores the constructed models in the server. When it is necessary to perform baseflow segmentation calculation for areas with similar environmental characteristics to the preset site and lack of conductivity, the contribution recognition model and the conductivity regression model provided by the present invention can be used to obtain a conductivity data sequence that meets the requirements of the CMB method, thereby realizing the use of the high-precision CMB method to calculate baseflow in areas lacking conductivity.

[0045] First, the dynamic and static environmental parameters of the stations in the study area are collected; the dynamic environmental parameters can include daily precipitation time series, temperature time series, evapotranspiration time series, flow time series and EC, etc.; the static environmental parameters can include altitude, slope, sand ratio, clay ratio, annual average precipitation, annual average temperature, annual average potential evaporation, etc.

[0046] Furthermore, the regions with similar environmental characteristics such as climate, vegetation, soil type and geological conditions in the study area are divided into an ecological zone. The preset sites of the present invention can be divided into the Western Mountains ecological zone WM (Western Mountains), the Northern Plains ecological zone NP (Northern Plains), the Southern Plains ecological zone SP (Southern Plains) and the Temperate Plains ecological zone TP (Temperate Plains). The following takes the Southern Plains ecological zone SP as an example to construct a feature contribution recognition model and a conductivity regression model. The construction methods of the other three ecological zones are the same as the construction method of the Southern Plains ecological zone SP.

[0047] The main control parameters of the SP ecological zone in the Missouri River Basin can be used. The main control parameters include high vegetation leaf index and flow, and the main control dynamic parameters include elevation, drought index, annual average precipitation, annual average potential evaporation, snowfall ratio and annual average temperature.

[0048] Preferably, establishing a feature contribution recognition model may include: performing data preprocessing on the hydrological feature data in the multiple ecological zones to obtain a sample data set including a first training set and a first test set; using the first training set to perform model training on the network model to obtain a first feature contribution recognition model; and using the first test set to perform recognition accuracy testing on the first feature contribution recognition model.

[0049] If the recognition accuracy of the first feature contribution recognition model meets the preset recognition accuracy requirement, the first feature contribution recognition model will be used as the feature contribution recognition model; if the recognition accuracy of the first feature contribution recognition model does not meet the recognition accuracy requirement, the network model will continue to be trained until a feature contribution recognition model that meets the recognition accuracy requirement is obtained.

[0050] Preferably, the first feature contribution recognition model includes determining a plurality of algorithm models; the plurality of algorithm models include the formula:

[0051] FI(X j )=∑ 树 ∑ 节点t ΔMSE j (t) (1)

[0052]

[0053]

[0054] In formulas (1) to (3), FI is the feature contribution, N is the number of samples, and y is i is the true value of the i-th sample, is the model calculation value of the i-th sample, t is the t-th node, N L is the number of samples of the adjacent nodes on the left side of the tth node, N R is the number of samples of the adjacent nodes on the right side of the t-th node, Nt is the number of samples of the t-th node, t R is the right adjacent node of the tth node, t L is the left adjacent node of the t-th node, and MSE is the mean square error reduced by the feature when splitting the node.

[0055] Specifically, various data of the southern plains ecoregion SP are first integrated. 80% of the integrated data constitute the first training set of the feature recognition model, and the remaining 20% ​​is used as the first test set. The first training set is used to train the network model, and the first test set is used to evaluate the recognition accuracy of the feature recognition model. Among them, the network model preferably uses the random forest regression model RF-Regressor (Random Forest-Regressor, RF-Regressor) model as the feature recognition model in the present invention, and n_estimators can be set to 100 and random_state can be set to 42 in the algorithm.

[0056] The importance of a feature in EC regression is measured by the cumulative value of the mean squared error (MSE) reduced when the feature splits the node. The more times the feature is split and the greater the error reduction, the higher the importance of the feature. Taking into account the impact of dynamic and static parameters on the model regression results, the importance FI of each feature is determined by formulas (1) to (3); that is, the contribution FI of each feature is obtained. Specifically, the importance of each feature can be output through the attribute feature_importances of the RF-Regressor model, and the features with a sum of mean squared errors greater than or equal to 80% are selected as the main control parameters for the EC regression of the ecological zone.

[0057] Based on this, the training set can be used to train the RF-Regressor model, and the first feature contribution identification model can be obtained by self-learning or semi-supervised learning. The test set is then used to verify the first feature contribution identification model to determine whether the main control parameters output by the first feature contribution identification model are different from the actual main control parameters. If they are the same as the actual main control parameters or the difference is not large, it means that the first feature contribution identification model meets the requirements, and the first feature contribution identification model can be used as a feature identification model that can be applied to other watersheds with similar environmental characteristics. If the difference is large, the first training set is used or data is re-collected to continue training the RF-Regressor model until the main control parameters obtained by the model after training are the same as or not much different from the actual main control parameters in the Missouri River Basin.

[0058] Furthermore, the establishment of the conductivity regression model may include: using the feature contribution identification model to perform feature identification on the hydrological feature data of the plurality of ecological zones to obtain a plurality of main control parameters for the conductivity regression of the plurality of ecological zones; the plurality of main control parameters are parameters whose sum of mean square errors is greater than or equal to 80%; and discretely sampling the plurality of main control parameters for a target number of times at weekly intervals to obtain a second training set of a target time length.

[0059] The network model is trained based on the second training set to obtain a first conductivity regression model; specifically, during the model training process, the daily-scale dynamic environmental parameters and static environmental parameters in the second training set are used as input, and the daily-scale EC is used as output, and the network model is subjected to machine learning or semi-supervised learning to obtain the first conductivity regression model.

[0060] The prediction accuracy of the first conductivity regression model is verified by using the second test set to obtain the verification result of the model fitting of the first conductivity regression model; the second test set is the data other than conductivity in the hydrological characteristic data of the preset site. Specifically, during the model testing process, the dynamic environmental parameters and static environmental parameters of the environment on a daily scale are used as input to determine whether the first conductivity regression model can output a regression EC on a daily scale, so as to determine whether the regression EC on a daily scale deviates from the measured EC on a daily scale of the preset site.

[0061] If the verification result indicates that the prediction accuracy of the first conductivity regression model meets the prediction accuracy requirement, the first conductivity regression model is used as the conductivity regression model.

[0062] If the verification result indicates that the prediction accuracy of the first conductivity regression model does not meet the prediction accuracy requirement, the network model continues to be trained until a conductivity regression model that meets the prediction accuracy requirement is obtained.

[0063] It should be noted that the prediction accuracy indicates the deviation between the obtained regression EC and the measured EC, and the deviation can be determined according to the specific application scenario.

[0064] The use of the second test set to verify the prediction accuracy of the first conductivity regression model may include using the formula:

[0065]

[0066] Calculate the root mean square error, which is used to evaluate the prediction accuracy of the conductivity regression model; where RMSE is the root mean square error, EC mod,i is the regression EC obtained by the model at time i, is the average value obtained from the measured EC, and n is the number of data.

[0067] Specifically, the main control parameters determined by the contribution identification model can be discretely sampled at intervals of T = 7 days to simulate the situation where the hydrological station monitors EC at a weekly frequency. The time interval here can be modified according to the specific conditions of the study area station and monitoring conditions, such as simulating the situation where the hydrological station monitors EC at a daily frequency; this description only takes T = 7 days as an example.

[0068] It should be noted that in areas where EC data are scarce, the amount of data required to segment the base flow directly determines the economic cost and generalizability of the model. Therefore, in order to improve the economy and generalizability of the model, it is necessary to determine the optimal data length of the second training set.

[0069] Therefore, discrete sampling of the plurality of master control parameters for a target number of times at weekly intervals to obtain a second training set of a target time length may specifically include:

[0070] First, the amount of training data in weekly intervals is subjectively set to 52, 78, 104, 130, 156, 182, 208, and 260, respectively, to represent the data of sites with a time length of 12 months, 18 months, 24 months, etc. That is, the target time length can include 12 months, 18 months, or 24 months.

[0071] Secondly, the target number of discrete samplings of the plurality of master control parameters is performed at weekly intervals, such as 52, 78, 104, 130, 156, 182, 208 and 260 times, respectively, to form a training set of corresponding data volume. That is, the target number of samplings may include 52, 78, 104, 130, 156, 182, 208 or 260.

[0072] It should be noted that, assuming that the sampling interval of the training set data is weekly, that is, one number is taken per week, when the amount of training set data is 52, 52 * 7 days / 30 days = 12 months, and so on.

[0073] The present invention preferably uses the RF-Regressor model as the regression model for continuous EC, and uses hyperparameter tuning to determine the parameters of the RF model. GridSearchCV is used to optimize the four parameters of the RF model, including max_depth, the maximum depth of the decision tree; n_estimators, the number of decision trees in the random forest; min_samples_leaf, the minimum number of samples for each leaf node; min_samples_split, the minimum number of samples required for splitting nodes, and outputs the best parameter combination of the RF model. For example: the remaining main control parameters are processed to the same frequency as the EC data, and then the optimal parameter combination required for the RF model during EC regression is identified, and max_depth = 8, min_samples_leaf = 2, min_samples_split = 2, and n_estimators = 250 are determined.

[0074] The conductivity regression model can also be cross-validated and evaluated. For example, after determining the best parameter combination, a 5-fold cross validation (cv=5) is used to evaluate the performance of the model. 2 To reflect the model fitting situation.

[0075] Furthermore, the input data can be preprocessed. The continuous data except EC in the main control parameters are used as the test set, EC is the target variable, and the remaining parameters are feature variables. The missing values ​​and abnormal values ​​in the imported data are first processed by the algorithm, and then the feature data is standardized using StandardScaler.

[0076] Finally, the root mean square error (RMSE) can be calculated using formula (4).

[0077] Based on this, the above method can be used to perform 5 sampling and calculations to obtain the corresponding root mean square error value, that is, 52, 78, 104, 130, 156, 182, 208 and 260 samples are taken from the discrete data to form the training set of the corresponding data volume, and the training model is trained to obtain the RMSE of the model regression result. The obtained RMSE is subjected to normal distribution and T-test, and the shortest one is selected from each target number with no significant difference (p>0.05) as the acceptable optimal target number; the experiment shows that sampling 156 times is the minimum acceptable monitoring period and the optimal data length of the training set; therefore, in the conductivity-deficient area with similar environmental characteristics, the method of sampling the hydrological characteristic data 156 times can be used for EC regression prediction to minimize the use cost while ensuring the accuracy of the prediction results.

[0078] In summary, the model can be trained using a training set with minimal data to improve the training efficiency of the model; and the test set can be used to input environmental characteristic variables other than EC to verify whether the target variable EC can be obtained; thereby confirming the prediction accuracy of the conductivity regression model.

[0079] Furthermore, the EC regression results and visualization output can be combined. The time series table of the regressed EC can be output and visualized with the measured EC for better data comparison.

[0080] Furthermore, based on the regressed EC and hydrological characteristic data, the CMB method can be used to perform base flow segmentation calculation on the preset site to obtain the base flow of the preset site; and the accuracy of the regressed EC can be further evaluated.

[0081] For details, please refer to Figures 2 to 3 , Figure 2 A comparison diagram of model regression EC and measured EC for a base flow calculation method for conductivity-deficient areas provided by the present invention; Figure 3 A comparison chart of base flow calculation method for conductivity-deficient areas provided by the present invention and base flow calculated by ECK empirical value method.

[0082] exist Figure 2In the figure, the EC curve is constructed by taking the data of the 07096000 station as an example. The horizontal axis represents time, in days; the vertical axis represents the conductivity EC, in μs / cm; the curve composed of black dots is the measured EC curve, and the curve composed of blue dots is the regression conductivity EC curve predicted by the model constructed by the method of the present invention. Figure 1 It can be concluded without a doubt that: Select R 2 The RMSE evaluation model regression results are used to evaluate the conductivity regression model constructed by the present invention, and the model regression fit R 2 The EC obtained by the conductivity regression model is well matched with the measured EC data in terms of time variation, which indicates that the characteristic contribution recognition model and the conductivity regression model constructed by the method of the present invention have a good fit with the measured EC data and meet the design requirements.

[0083] exist Figure 3 In the figure, the horizontal axis represents time in days, and the vertical axis represents base flow in m. 3 / s; the curve composed of black dots is the measured data curve of base flow, the curve composed of blue diamonds is the model regression curve, and the curve composed of pink dots is the curve obtained after the base flow segmentation calculation using the ECK method. In order to further highlight the superiority of the method provided by the present invention, the segmentation results of the commonly used ECK empirical value method are introduced for comparison, and the RMSE 模型 Set to 4.70, RMSE ECK Set to 7.93. Figure 3 It can be seen that compared with the baseflow segmentation results of the ECK method, the regression results of the method provided in this specification are more consistent with the measured results, and the calculated RMSE is lower. It also shows that the regression EC obtained by the method provided in this specification meets the scale requirements of EC when the high-precision CMB method is used for baseflow segmentation calculation; thus, the high-precision baseflow segmentation method can be applied to areas with insufficient data, and the baseflow segmentation accuracy obtained is higher than that of the commonly used ECK method.

[0084] Preferably, in step 120, the use of the feature contribution recognition model to identify the contribution of the target hydrological characteristic data to obtain target parameter combination data for conductivity regression of the target site may include: dividing the target hydrological characteristic data into ecological zones to obtain multiple target ecological zones; inputting the hydrological characteristic data of the multiple target ecological zones into the feature contribution recognition model to obtain the contribution of each feature; using feature parameters with a contribution greater than or equal to 80% as target parameters of the multiple target ecological zones; and performing data combination processing on the target parameters of the multiple target ecological zones to obtain target parameter combination data for conductivity regression of the target site.

[0085] It should be noted that the method used in dividing the target site into ecological zones is the same as the method used in dividing the preset site into ecological zones, and will not be repeated here. Therefore, the target site has the same environmental characteristics as the preset site, and the ecological zones are divided in the same way. Therefore, the feature contribution model established based on the hydrological characteristic data of the preset site can be used to identify the contribution of the features in multiple ecological zones, and the contribution of each feature can be obtained. The features with a contribution greater than 80% are further used as target parameter features, and finally all target parameter features of multiple target ecological zones are combined to obtain the target parameter combination data for conductivity regression of the target site. Similarly, it can be understood that the conductivity regression model constructed by the preset site can also be used to predict the target conductivity regression data for the target site; thus, the base flow of the target site can be segmented and calculated using the CMB method based on the target hydrological characteristic data and the target conductivity regression data to obtain the base flow of the target site.

[0086] Preferably, in step 140, based on the target hydrological characteristic data and the target conductivity regression data, using the CMB method to perform base flow segmentation calculation on the target site to obtain the base flow of the target site may include:

[0087] Using the formula:

[0088]

[0089] Calculate the base flow of the target site; where q BF is the base traffic of the target site, EC RO The minimum conductivity and EC of each year BF is the annual maximum conductivity, Q is the target hydrological characteristic data, and EC is the target conductivity regression data.

[0090] Specifically, the parameter EC can be determined by the daily EC data obtained through model regression. RO 128.69μs / cm, EC BF The daily base flow rate is 338.97 μs / cm. Substituting the determined parameters, daily conductivity and collected Q data into formula (5), the daily base flow rate is obtained.

[0091] In a second aspect, the present invention provides a base flow calculation device for use in areas with low conductivity. Figure 4 , Figure 4 A schematic structural diagram of a base flow calculation device for use in areas with a lack of electrical conductivity provided by the present invention.

[0092] exist Figure 4 In the embodiment, the computing device may include:

[0093] The acquisition module 410 is used to acquire target hydrological characteristic data of a target site, wherein the target hydrological characteristic data at least includes dynamic environmental parameters and static environmental parameters related to base flow generation; the target site is an area with environmental characteristics similar to those of a preset site and lacking in electrical conductivity.

[0094] The contribution recognition module 420 is used to identify the contribution of the target hydrological characteristic data using a characteristic contribution recognition model to obtain target parameter combination data for conductivity regression of the target site; the target parameter combination data represents parameter combination data whose conductivity regression contribution is greater than a preset threshold.

[0095] The conductivity regression prediction module 430 is used to perform prediction based on the target parameter combination data and according to the target time scale using a conductivity regression model to obtain target conductivity regression data for the target site.

[0096] The calculation module 440 is used to perform base flow segmentation calculation on the target site by using the conductivity mass balance method based on the target hydrological characteristic data and the target conductivity regression data to obtain the base flow of the target site.

[0097] Based on this, the present invention provides a base flow calculation device for areas with insufficient conductivity, which uses an acquisition module 410 to obtain target hydrological characteristic data of a target site, wherein the target hydrological characteristic data at least includes dynamic environmental parameters and static environmental parameters related to base flow generation; the target site is an area with similar environmental characteristics to a preset site and insufficient conductivity; a contribution recognition module 420 is further used to identify the contribution of the target hydrological characteristic data to obtain target parameter combination data for conductivity regression of the target site; the target parameter combination data represents parameter combination data with a conductivity regression contribution greater than a preset threshold; and a conductivity regression prediction module 430 is used to predict based on the target parameter combination data according to a target time scale using a conductivity regression model to obtain target conductivity regression data for the target site; finally, a calculation module 440 is used to perform base flow segmentation calculation on the target site using a conductivity mass balance method based on the target hydrological characteristic data and the target conductivity regression data to obtain the base flow of the target site; thereby, the conductivity mass balance method can be used to perform base flow segmentation calculation on areas with insufficient conductivity.

[0098] Although the present invention is described herein in conjunction with various embodiments, in the process of implementing the claimed invention, those skilled in the art may understand and implement other variations of the disclosed embodiments by viewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "one" or "an" does not exclude multiple situations. A single processor or other unit may implement several functions listed in the claims. Certain measures are recorded in different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0099] Although the present invention has been described in conjunction with specific features and embodiments thereof, it is apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present invention. Accordingly, this specification and the accompanying drawings are merely exemplary illustrations of the present invention as defined by the appended claims and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present invention. Obviously, those skilled in the art may make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, the present invention is intended to include such modifications and variations if they fall within the scope of the claims of the present invention and their equivalents.

Claims

1. A method for calculating base flow in areas with low conductivity, characterized in that: include: Obtaining target hydrological characteristic data of a target site, wherein the target hydrological characteristic data at least includes dynamic environmental parameters and static environmental parameters related to base flow generation; the target site is an area with similar environmental characteristics to the preset site and lacking in electrical conductivity; The target hydrological characteristic data is identified for contribution by using a characteristic contribution identification model to obtain target parameter combination data for conductivity regression of the target site; the target parameter combination data represents parameter combination data whose conductivity regression contribution is greater than a preset threshold; Based on the target parameter combination data, according to the target time scale, a conductivity regression model is used to perform prediction to obtain target conductivity regression data for the target site; Based on the target hydrological characteristic data and target conductivity regression data, the conductivity mass balance method is used to perform base flow segmentation calculation on the target site to obtain the base flow of the target site.

2. The method according to claim 1, characterized in that The method of performing base flow segmentation calculation on the target site based on the target hydrological characteristic data and the target conductivity regression data using the conductivity mass balance method to obtain the base flow of the target site includes: Using the formula: Get the base flow of the target site; where q BF is the base traffic of the target site, EC RO The minimum conductivity and EC of each year BF is the annual maximum conductivity, Q is the target hydrological characteristic data, and EC is the target conductivity regression data.

3. The method according to claim 1, characterized in that The method of using a characteristic contribution recognition model to identify the contribution of the target hydrological characteristic data to obtain target parameter combination data for conductivity regression of the target site includes: Obtaining hydrological characteristic data of a preset site; the preset site is a site whose conductivity satisfies the base flow splitting calculation using the conductivity mass balance method; Dividing the hydrological characteristic data into ecological zones to obtain a plurality of ecological zones; the ecological zones are regions with similar environmental characteristics; the environmental characteristics include climate, vegetation, soil type and geological conditions; Based on the hydrological characteristic data of the plurality of ecological zones, the characteristic contribution recognition model and the conductivity regression model are established.

4. The method according to claim 3, characterized in that The step of establishing a feature contribution recognition model comprises: Performing data preprocessing on the hydrological characteristic data in the plurality of ecological zones to obtain a sample data set including a first training set and a first test set; Using the first training set to train the network model, to obtain a first feature contribution recognition model; Using the first test set to perform a recognition accuracy test on the first feature contribution recognition model; If the recognition accuracy of the first feature contribution recognition model meets the preset recognition accuracy requirement, the first feature contribution recognition model is used as the feature contribution recognition model; If the recognition accuracy of the first feature contribution recognition model does not meet the recognition accuracy requirement, the network model continues to be trained until a feature contribution recognition model that meets the recognition accuracy requirement is obtained.

5. The method according to claim 4, characterized in that The first feature contribution recognition model includes determining a plurality of algorithm models; A plurality of said algorithm models include formulas: Among them, FI is the feature contribution, N is the number of samples, and y i is the true value of the i-th sample, is the model calculation value of the i-th sample, t is the t-th node, N L is the number of samples of the adjacent nodes on the left side of the tth node, N R is the number of samples of the adjacent nodes on the right side of the t-th node, Nt is the number of samples of the t-th node, t R is the right adjacent node of the tth node, t L is the left adjacent node of the t-th node, and MSE is the mean square error reduced by the feature when splitting the node.

6. The method according to claim 3, characterized in that The establishment of the conductivity regression model comprises: The characteristic contribution recognition model is used to perform characteristic recognition on the hydrological characteristic data of the plurality of ecological zones, and a plurality of main control parameters for the conductivity regression of the plurality of ecological zones are obtained; the plurality of main control parameters are parameters whose sum of mean square errors is greater than or equal to 80%; discretely sampling the plurality of master control parameters for a target number of times at weekly intervals to obtain a second training set of a target time length; Performing model training on the network model based on the second training set to obtain a first conductivity regression model; The prediction accuracy of the first conductivity regression model is verified by using a second test set to obtain a verification result of the model fitting of the first conductivity regression model; the second test set is the data other than conductivity in the hydrological characteristic data of the preset site; If the verification result indicates that the prediction accuracy of the first conductivity regression model meets the prediction accuracy requirement, the first conductivity regression model is used as the conductivity regression model; If the verification result indicates that the prediction accuracy of the first conductivity regression model does not meet the prediction accuracy requirement, the network model continues to be trained until a conductivity regression model that meets the prediction accuracy requirement is obtained.

7. The method according to claim 6, characterized in that The use of the second test set to verify the prediction accuracy of the first conductivity regression model includes using the formula: Calculate the root mean square error, which is used to evaluate the prediction accuracy of the conductivity regression model; where RMSE is the root mean square error, EC mod,i is the regression EC obtained by the model at time i, is the average value obtained from the measured EC, and n is the number of data.

8. The method according to claim 1, characterized in that The method of using the characteristic contribution recognition model to identify the contribution of the target hydrological characteristic data to obtain the target parameter combination data for the conductivity regression of the target site includes: Dividing the target hydrological characteristic data into ecological zones to obtain a plurality of target ecological zones; Inputting the hydrological characteristic data of the plurality of target ecological zones into the characteristic contribution recognition model to obtain the contribution of each characteristic; Taking characteristic parameters with a contribution greater than or equal to 80% as target parameters of the plurality of target ecological zones; The target parameters of the plurality of target ecological zones are processed by data combination to obtain target parameter combination data for conductivity regression of the target site.

9. The method according to claim 1, characterized in that The dynamic environmental parameters include at least daily precipitation time series data, temperature time series data, evapotranspiration time series data and flow time series data, as well as electrical conductivity; the static environmental parameters include at least altitude, slope, sand particle ratio, clay particle ratio, annual average precipitation, annual average temperature and annual average potential evaporation.

10. A base flow calculation device for areas with poor conductivity, characterized in that: include: An acquisition module, the acquisition module is used to acquire target hydrological characteristic data of a target site, the target hydrological characteristic data at least including dynamic environmental parameters and static environmental parameters related to base flow generation; the target site is an area with similar environmental characteristics to the preset site and lacking conductivity; A contribution recognition module, wherein the contribution recognition module is used to identify the contribution of the target hydrological characteristic data using a characteristic contribution recognition model to obtain target parameter combination data for conductivity regression of the target site; the target parameter combination data represents parameter combination data whose conductivity regression contribution is greater than a preset threshold; A conductivity regression prediction module, which is used to predict the target conductivity regression data for the target site by using a conductivity regression model based on the target parameter combination data and according to the target time scale; A calculation module is used to perform base flow segmentation calculation on the target site by using a conductivity mass balance method based on the target hydrological characteristic data and the target conductivity regression data to obtain the base flow of the target site.

Images